Fix model card accuracy (format/filename)

README.md

@@ -27,14 +27,14 @@ Forkjoin.ai conversion of [deepseek-ai/DeepSeek-OCR](https://huggingface.co/deep
 ### With llama.cpp
 
 ```bash
-./llama-cli -m deepseek-ocr-gguf.gguf -p "Your prompt here" -n 256
+./llama-cli -m DeepSeek-OCR.Q4_K.gguf -p "Your prompt here" -n 256
 ```
 
 ### With Ollama
 
 Create a `Modelfile`:
 ```
-FROM ./deepseek-ocr-gguf.gguf
+FROM ./DeepSeek-OCR.Q4_K.gguf
 ```
 
 ```bash